Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912937317236736 |
|---|---|
| author | Tang, Yinghao Xie, Yupeng Feng, Yingchaojie Lan, Tingfeng Chen, Wei |
| author_facet | Tang, Yinghao Xie, Yupeng Feng, Yingchaojie Lan, Tingfeng Chen, Wei |
| contents | Interactive articles help readers engage with complex ideas through exploration, yet creating them remains costly, requiring both domain expertise and web development skills. Recent LLM-based agents can automate content creation, but naively applying them yields uncontrollable and unverifiable outputs. We present ViviDoc, a human-agent collaborative system that generates interactive educational documents from a single topic input. ViviDoc introduces a multi-agent pipeline (Planner, Executor, Evaluator) and the Document Specification (DocSpec), a human-readable intermediate representation that decomposes each interactive visualization into State, Render, Transition, and Constraint components. The DocSpec enables educators to review and refine generation plans before code is produced, bridging the gap between pedagogical intent and executable output. Expert evaluation and a user study show that ViviDoc substantially outperforms naive agentic generation and provides an intuitive editing experience. Our project homepage is available at https://vividoc-homepage.vercel.app/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01912 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration Tang, Yinghao Xie, Yupeng Feng, Yingchaojie Lan, Tingfeng Chen, Wei Computation and Language Artificial Intelligence Interactive articles help readers engage with complex ideas through exploration, yet creating them remains costly, requiring both domain expertise and web development skills. Recent LLM-based agents can automate content creation, but naively applying them yields uncontrollable and unverifiable outputs. We present ViviDoc, a human-agent collaborative system that generates interactive educational documents from a single topic input. ViviDoc introduces a multi-agent pipeline (Planner, Executor, Evaluator) and the Document Specification (DocSpec), a human-readable intermediate representation that decomposes each interactive visualization into State, Render, Transition, and Constraint components. The DocSpec enables educators to review and refine generation plans before code is produced, bridging the gap between pedagogical intent and executable output. Expert evaluation and a user study show that ViviDoc substantially outperforms naive agentic generation and provides an intuitive editing experience. Our project homepage is available at https://vividoc-homepage.vercel.app/. |
| title | Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2603.01912 |